"Creating Playwright Tests by Exploring a Website and Generating Test Cases" matching MCP servers:

Gives LLMs full control over VS Code — click UI elements, type code, run commands, take screenshots, read editor state, and record GIFs.

An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.

Enables AI assistants to interact with Google's Jules coding agent API for autonomous coding tasks, allowing users to delegate bug fixes, refactoring, testing, and feature development with scheduling capabilities and human-in-the-loop approval workflows.

An authenticated OpenAI-compatible inference gateway with an async job broker that bridges a coding agent to a ChatGPT MCP worker, enabling ChatGPT to process inference requests via a tunnel.

An autonomous, extensible LLM build orchestrator. Give it a repo and a goal; it decomposes the goal into tasks, edits code, and gates every change on build/tests/lint, reverting regressions. Polygot, cost-aware model selection, pluggable via entry points. Ships as an MCP server so any client can drive it in plain English.

A Model Context Protocol (MCP) server that wraps the dbt CLI tool, enabling AI coding agents to interact with dbt projects through standardized MCP tools. Developed by Mammoth Growth.

Enables agents to autonomously resolve GitHub issues by editing code, running tests, and opening pull requests, while enforcing guardrails that protect critical files and systems.

Turn rough requests into rigorously structured prompts for any coding agent. Quality-scored to ≥90/100 across 12 dimensions, calibrated on 1,000+ real coding cases.

MCP server for creating, monitoring, and managing Devin AI sessions.

A secure, containerized workspace for LLMs to autonomously code, test, and debug projects without risking the host machine.

Enables MCP clients to delegate routine coding tasks to a local model in isolated git worktrees, using test results as a gate and the client as the reviewer before changes are merged.

An MCP server that lets Claude Code delegate coding tasks such as code generation, review, refactoring, and test writing to a local Ollama instance running a Qwen3 model.

Enables AI agents to perform software engineering tasks inside an isolated, deterministic sandbox—exploring repositories, reproducing failures, applying patches, running tests, and verifying solutions against hidden suites through MCP tools.

The IDE for agents — read by symbol, edit against a revision, validate with your own build, revert. It is a local stdio MCP server for coding agents. It reads code by symbol with tree-sitter and real language servers (Go, Java, Scala, TypeScript, Python, Rust, Ruby), edits against a known revision and returns compiler diagnostics with each edit, runs the repository's own build, test etc.

Enables Claude Code to delegate bounded repository tasks to DeepSeek as a local sub-agent, handling exploration, routine changes, and test runs within a controlled workspace and budget.

Enables AI coding agents to compile, test, run, hot-swap, and debug Java applications incrementally through MCP, providing runtime feedback for verifying code changes.

AIContextBuilder (AICB): Roslyn MCP server for C#/.NET code intelligence. Gives coding agents semantic code analysis and navigation instead of text search: callers, change impact, implementations, dependency injection, covering tests, side effects, dead code and token-budgeted context. Installs as a dotnet tool and analyzes any csharp solution locally.

Autonomous coding pipeline exposed as an MCP server: plan, dispatch, review, and merge software stories through worktree-isolated agents. A frontier model (Claude) handles judgment — planning, review, risk adjudication — while a local model does the implementation, gated by TDD and a merge-time test rerun on the rebased branch.

Enables any LLM to drive your local Codex CLI in a sandboxed workspace, running coding tasks and generating images without needing an API key.

Enables MCP clients to control the local Codex CLI, including running and resuming agent sessions, forking, code review, applying diffs, and generating images, with background execution for long-running tasks.